© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88809
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åij½ä¸Ń
    -0.28
    evin
    -0.27
    htag
    -0.26
    è¶ģ
    -0.25
    å¤įèĭı
    -0.23
    ä¸ĩè¾Ĩ
    -0.23
     Inject
    -0.22
    ç½ijç»ľä¼łæĴŃ
    -0.22
    andard
    -0.22
     McMahon
    -0.22
    POSITIVE LOGITS
     lean
    0.28
    æµģ失
    0.28
     ide
    0.26
    DS
    0.23
    aba
    0.23
    leveland
    0.22
     unintention
    0.22
    åĬŀçIJĨ
    0.22
     substitute
    0.22
     isolation
    0.22
    Activations Density 0.060%

    No Known Activations

    This feature has no known activations.